{"id":"https://openalex.org/W7164016107","doi":"https://doi.org/10.48550/arxiv.2606.08993","title":"LEAF: A Learning-Enabled ADMM Framework for Accelerated Convex Optimization","display_name":"LEAF: A Learning-Enabled ADMM Framework for Accelerated Convex Optimization","publication_year":2026,"publication_date":"2026-06-08","ids":{"openalex":"https://openalex.org/W7164016107","doi":"https://doi.org/10.48550/arxiv.2606.08993"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2606.08993","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.08993","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2606.08993","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5126111881","display_name":"Binh Nguyen","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Nguyen, Binh","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5138228992","display_name":"Trinh Tran","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tran, Trinh","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5138256655","display_name":"Truong X. Nghiem","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Nghiem, Truong X.","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11612","display_name":"Stochastic Gradient Optimization Techniques","score":0.7063999772071838,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T11612","display_name":"Stochastic Gradient Optimization Techniques","score":0.7063999772071838,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10500","display_name":"Sparse and Compressive Sensing Techniques","score":0.09019999951124191,"subfield":{"id":"https://openalex.org/subfields/2206","display_name":"Computational Mechanics"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10963","display_name":"Advanced Optimization Algorithms Research","score":0.021700000390410423,"subfield":{"id":"https://openalex.org/subfields/2612","display_name":"Numerical Analysis"},"field":{"id":"https://openalex.org/fields/26","display_name":"Mathematics"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/convexity","display_name":"Convexity","score":0.7222999930381775},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.638700008392334},{"id":"https://openalex.org/keywords/convergence","display_name":"Convergence (economics)","score":0.6057000160217285},{"id":"https://openalex.org/keywords/convex-optimization","display_name":"Convex optimization","score":0.5982000231742859},{"id":"https://openalex.org/keywords/convex-function","display_name":"Convex function","score":0.5414000153541565},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.5113000273704529},{"id":"https://openalex.org/keywords/envelope","display_name":"Envelope (radar)","score":0.46219998598098755},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.4498000144958496},{"id":"https://openalex.org/keywords/regular-polygon","display_name":"Regular polygon","score":0.4465999901294708}],"concepts":[{"id":"https://openalex.org/C72134830","wikidata":"https://www.wikidata.org/wiki/Q5166524","display_name":"Convexity","level":2,"score":0.7222999930381775},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.638700008392334},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.6057000160217285},{"id":"https://openalex.org/C157972887","wikidata":"https://www.wikidata.org/wiki/Q463359","display_name":"Convex optimization","level":3,"score":0.5982000231742859},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.5877000093460083},{"id":"https://openalex.org/C145446738","wikidata":"https://www.wikidata.org/wiki/Q319913","display_name":"Convex function","level":3,"score":0.5414000153541565},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.5113000273704529},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.48080000281333923},{"id":"https://openalex.org/C65155139","wikidata":"https://www.wikidata.org/wiki/Q5380912","display_name":"Envelope (radar)","level":3,"score":0.46219998598098755},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.4498000144958496},{"id":"https://openalex.org/C112680207","wikidata":"https://www.wikidata.org/wiki/Q714886","display_name":"Regular polygon","level":2,"score":0.4465999901294708},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.42100000381469727},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.399399995803833},{"id":"https://openalex.org/C137836250","wikidata":"https://www.wikidata.org/wiki/Q984063","display_name":"Optimization problem","level":2,"score":0.38109999895095825},{"id":"https://openalex.org/C12108790","wikidata":"https://www.wikidata.org/wiki/Q2234833","display_name":"Convex analysis","level":4,"score":0.37549999356269836},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.36629998683929443},{"id":"https://openalex.org/C57869625","wikidata":"https://www.wikidata.org/wiki/Q1783502","display_name":"Rate of convergence","level":3,"score":0.3447999954223633},{"id":"https://openalex.org/C50862404","wikidata":"https://www.wikidata.org/wiki/Q3075259","display_name":"Proper convex function","level":5,"score":0.3398999869823456},{"id":"https://openalex.org/C68339613","wikidata":"https://www.wikidata.org/wiki/Q1549489","display_name":"Speedup","level":2,"score":0.32710000872612},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3025999963283539},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.2881999909877777},{"id":"https://openalex.org/C91873725","wikidata":"https://www.wikidata.org/wiki/Q3445816","display_name":"Function approximation","level":3,"score":0.27799999713897705},{"id":"https://openalex.org/C179799912","wikidata":"https://www.wikidata.org/wiki/Q205084","display_name":"Computational complexity theory","level":2,"score":0.26570001244544983},{"id":"https://openalex.org/C79187972","wikidata":"https://www.wikidata.org/wiki/Q2654791","display_name":"Conic optimization","level":5,"score":0.25690001249313354},{"id":"https://openalex.org/C64980692","wikidata":"https://www.wikidata.org/wiki/Q16191959","display_name":"Symbolic convergence theory","level":3,"score":0.25119999051094055}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2606.08993","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.08993","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2606.08993","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.08993","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"We":[0],"propose":[1],"LEAF,":[2],"a":[3,33,66,81],"learning-enabled":[4],"ADMM":[5,49,146],"framework":[6,79],"for":[7],"accelerated":[8],"convex":[9,85],"optimization.":[10],"The":[11,78],"key":[12,109],"idea":[13],"is":[14],"to":[15,43,144,156],"approximate":[16],"the":[17,21,44,97,100,113,130,137],"Moreau":[18,46,68],"envelope":[19],"of":[20,84,112,125],"objective":[22],"function":[23],"using":[24],"an":[25,157],"Input":[26],"Convex":[27],"Neural":[28],"Network":[29],"(ICNN),":[30],"resulting":[31],"in":[32],"learned":[34,131],"model":[35,72],"that":[36,59,136],"preserves":[37],"convexity":[38,94],"and":[39,51,74,89,118,127],"smoothness.":[40],"This":[41],"leads":[42],"proposed":[45,101,138],"Envelope":[47],"Learning":[48],"(MEL-ADMM)":[50],"its":[52],"splitting":[53],"variant":[54],"sMEL-ADMM.":[55],"Unlike":[56],"existing":[57],"approaches":[58],"learn":[60],"high-dimensional":[61],"operators":[62],"directly,":[63],"LEAF":[64],"learns":[65],"scalar-valued":[67],"envelope,":[69],"significantly":[70],"reducing":[71,148],"complexity":[73],"improving":[75],"data":[76],"efficiency.":[77],"accommodates":[80],"broad":[82],"class":[83],"problems":[86],"with":[87,122],"smooth":[88],"non-smooth":[90],"objectives.":[91],"By":[92],"embedding":[93],"explicitly":[95],"through":[96],"ICNN":[98],"architecture,":[99],"approach":[102],"maintains":[103],"high":[104],"approximation":[105],"accuracy":[106],"while":[107,147,163],"preserving":[108],"structural":[110],"properties":[111],"optimization":[114],"problem.":[115],"Both":[116],"MEL-ADMM":[117],"sMEL-ADMM":[119],"are":[120],"developed":[121],"theoretical":[123],"guarantees":[124],"convergence":[126,141],"feasibility":[128],"under":[129],"model.":[132],"Rigorous":[133],"analysis":[134],"shows":[135],"methods":[139],"achieve":[140],"rates":[142],"comparable":[143],"classical":[145],"per-iteration":[149],"computational":[150],"cost.":[151],"Numerical":[152],"experiments":[153],"demonstrate":[154],"up":[155],"order-of-magnitude":[158],"speedup":[159],"over":[160],"state-of-the-art":[161],"solvers":[162],"maintaining":[164],"low":[165],"optimality":[166],"gaps":[167]},"counts_by_year":[],"updated_date":"2026-07-28T07:46:37.118299","created_date":"2026-06-10T00:00:00"}